Finite sample properties for the semiparametric estimation of the intercept of a censored regression model

摘要

The finite sample properties of parametric and semiparametric estimates of a CRM are compared. The latter are considered since the standard techniques produce inconsistent estimates when distributional assumption does not hold. The particular focus is on the estimation of the intercept of the 'outcome' equation of the model when Heckman's normality assumption does not hold.